Characterization Of Hepatocellular Carcinoma Research Articles

Machine learning-based identification of contrast-enhancement phase of computed tomography scans.

Contrast-enhanced computed tomography scans (CECT) are routinely used in the evaluation of different clinical scenarios, including the detection and characterization of hepatocellular carcinoma (HCC). Quantitative medical image analysis has been an exponentially growing scientific field. A number of studies reported on the effects of variations in the contrast enhancement phase on the reproducibility of quantitative imaging features extracted from CT scans. The identification and labeling of phase enhancement is a time-consuming task, with a current need for an accurate automated labeling algorithm to identify the enhancement phase of CT scans. In this study, we investigated the ability of machine learning algorithms to label the phases in a dataset of 59 HCC patients scanned with a dynamic contrast-enhanced CT protocol. The ground truth labels were provided by expert radiologists. Regions of interest were defined within the aorta, the portal vein, and the liver. Mean density values were extracted from those regions of interest and used for machine learning modeling. Models were evaluated using accuracy, the area under the curve (AUC), and Matthew's correlation coefficient (MCC). We tested the algorithms on an external dataset (76 patients). Our results indicate that several supervised learning algorithms (logistic regression, random forest, etc.) performed similarly, and our developed algorithms can accurately classify the phase of contrast enhancement.

Diagnostic Values of the Liver Imaging Reporting and Data System in the Detection and Characterization of Hepatocellular Carcinoma: A Systematic Review and Meta-Analysis.

This review was undertaken to assess the diagnostic value of the Liver Imaging Reporting and Data System (LI-RADS) in patients with a high risk of hepatocellular carcinoma (HCC). Google Scholar, PubMed, Web of Science, Embase, PROQUEST, and Cochrane Library, as the international databases, were searched with appropriate keywords. Using the binomial distribution formula, the variance of all studies was calculated, and using Stata version 16 (StataCorp LLC, College Station, TX, USA), the obtained data were analyzed. Using a random-effect meta-analysis approach, we determined the pooled sensitivity and specificity. Utilizing the funnel plot and Begg's and Egger's tests, we assessed publication bias. The results exhibited pooled sensitivity and pooled specificity of 0.80% and 0.89%, respectively, with a 95% confidence interval (CI) of 0.76-0.84 and 0.87-0.92, respectively. The 2018 version of LI-RADS showed the greatest sensitivity (0.83%; 95% CI0.79-0.87; I 2= 80.6%; P < 0.001 for heterogeneity; T 2 =0.001). The maximum pooled specificity was detected in LI-RADS version 2014 (American College of Radiology, Reston, VA, USA; 93.0%; 95% CI89.0-96.0; I 2= 81.7%; P < 0.001 for heterogeneity; T 2= 0.001). In this review, the results of estimated sensitivity and specificity were satisfactory. Therefore, this strategy can serve as an appropriate tool for identifying HCC.

Characterization of hepatocellular carcinoma in Mansoura university Hospitals: A case-control study of risk factors.

Characterization of hepatocellular carcinoma in Mansoura university Hospitals: A case-control study of risk factors.

Diagnosis of Hepatocellular Carcinoma Using Gd-EOB-DTPA MR Imaging.

Gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA; Gadoxetic acid; Gadoxetate disodium) is a hepatocyte-specific MR contrast agent. It acts as an extracellular contrast agent in the early phase after intravenous injection, and then is taken up by hepatocytes later. Using this contrast agent, we can evaluate the hemodynamics of the liver and liver tumors, and can therefore improve the detection and characterization of hepatocellular carcinoma (HCC). Gd-EOB-DTPA helps in the more accurate detection of hypervascular HCC than by other agents. In addition, Gd-EOB-DTPA can detect hypovascular HCC, which is an early stage of the multi-stage carcinogenesis, with a low signal in the hepatobiliary phase. In addition to tumor detection and characterization, Gd-EOB-DTPA contrast-enhanced MR imaging can be applied for liver function evaluation and prognoses evaluation. Thus, Gd-EOB-DTPA plays an important role in the diagnosis of HCC. However, we have to employ optimal imaging techniques to improve the diagnostic ability. In this review, we aimed to discuss the characteristics of the contrast media, optimal imaging techniques, diagnosis, and applications.

Pathological and Cytological Studies on Hepatocellular Carcinoma in Cattle Slaughtered at Bishoftu Elfora Abattoir, Central Ethiopia.

Hepatocellular carcinoma (HCC) is one of the most common neoplasms that has been described in many domestic animal species. Hence, the disease has significant economic importance; thus, this study aimed to describe the cytopathological characteristics of hepatocellular carcinomas in cattle slaughtered at Bishoftu Elfora Abattoir, Central Ethiopia. A cross-sectional study design with a purposive sampling technique was performed from October 2017 to May 2018 using macroscopic, histopathologic, and cytological methods. For that matter, a total of sixty cattle were assessed for the presence of a hepatic tumor; however, only 1/60 (0.6%) case was found to be affected by hepatocellular carcinomas. On gross examination, hepatocellular carcinomas exhibited soft, white, multifocal nodules (10–40 mm in diameter) on different lobes of the liver. On the cut surface, the tumor revealed a sharply circumscribed border and was divided into lobules by thin connective tissue. The central zone of the tumors exhibited depression with a whitish fibrous area. Moreover, on histopathology, the tumors divulged unencapsulated carcinomatous lesions consisting of a thick, compact, somewhat ambiguous trabecular pattern of arrangement that was unglued by thin collagenous stroma. Cytological studies suggest that the tumor cells showed anisocytosis, anisokaryosis, prominent nucleoli, multinuclearity, palisading arrangements of neoplastic cells, increased N : C ratios, light eosinophilic cytoplasm, high mitotic index, and cytoplasmic and intranuclear vacuoles. In conclusion, cytopathological findings support a diagnosis of HCC in the liver; thus, further studies with a large sample size and use of immunohistochemistry are important for further characterization of hepatocellular carcinomas in cattle.

Differences Between CT-Perfusion and Biphasic Contrast-enhanced CT for Detection and Characterization of Hepatocellular Carcinoma: Potential Explanations for Discrepant Cases.

To compare the diagnostic value of liver perfusion computed tomography (PCT) and biphasic contrast-enhanced CT (bpCECT) for detection and characterization of hepatocellular carcinoma (HCC), and to identify potential causes for inter-modal discrepancies. In this retrospective study, 162 cases with a total of 325 HCC-typical lesions were evaluated using both PCT and bpCECT (mean time between examinations=15 days, range=0-13 days). HCC diagnosis was performed by multi-modality imaging including lesion growth at follow-up. For PCT, a total acquisition time of 40 s (26 measurements) each 1.5 s using 80 kV and 100 mAs, as well as 50 ml iodine contrast agent (at 5 ml/s) covering the entire liver was used. Mean arterial liver perfusion (ALP), portal venous perfusion (PVP) and hepatic arterial index (HPI) for both tumor and non-involved liver parenchyma; mean blood flow, blood volume and k-trans for tumor were quantified. Tumor localization, and size were registered. bpCECT consisted of unenhanced, arterial (30-33 s delay), and portal-venous (70-75 s) phases performed using 120 kV, 200-250 mAs, thin-slice reformates (<1 mm), 100 ml contrast agent (at 3 ml/s) followed by 50 ml saline flush. Finally, we divided the results according to detection by PCT only (i.e. missed by pbCECT), and by both PCT and pbCECT. PCT detected 272 lesions compared to 217 with bpCECT only. HCCs in liver segments 4 and 5 were significantly better detected by PCT (p<0.005). Furthermore, PCT detected significantly smaller HCCs than did bpCECT (p<0.001). Lesions detected by both methods had significantly higher mean ALP (p=0.03) and HPI (p=0.02), and lower mean PVP (p=0.01). Tumor blood flow, blood volume and k-trans proved not to be significant for lesion detection. The mean ALP, HPI, and PVP in inconspicuous cirrhotic liver were also not significant for lesion detection. The PVP(tumor)/HPI(liver) ratio of detected lesions was significantly higher for PCT alone (p=0.04). Pretreated, still vital lesions were better detected by bpCECT. Detection of smaller HCC lesions, lesions located in liver segments 4 and 5, as well as lesions presenting lower ALP and HPI, and higher PVP(tumor)/HPI(liver) ratio was better using both methods, emphasizing the important role of PCT.

Abstract PO-055: Global immune characterization of hepatocellular carcinoma identifies macrophage and T cell subsets related to disease progression

Abstract Diverse immune cells in the tumor microenvironment form a complex ecosystem, but our knowledge of their heterogeneity and dynamics within hepatocellular carcinoma (HCC) remains poorly understood. We assess the plasticity and phenotypes of immune cells within HCC microenvironment at single-cell level. We performed single-cell RNA sequencing on 41,698 immune cells from 7 pairs of HCC tumors and nontumor liver tissues. We combined bioinformatic analyses, flow cytometry and multiplex immunohistochemistry to assess the heterogeneity of different immune subsets in functional characteristics, transcriptional regulation, phenotypic switching, and interactions. We identified 29 immune subsets of myeloid cells, NK cells, and lymphocytes with unique transcriptomic profiles in HCC. A highly complex immunological network was shaped by immune subsets with diverse characteristics that can transit among different states and mutually engage through intercellular communication. Notably, we identified a subset of M2 macrophage with high expression of CCL18 and transcription factor CREM that was enriched in advanced HCC patients, and potentially participated in tumor progression. We also detected a new subset of activated CD8+ T cells highly expressing XCL1 that correlated with better patient survival, and possibly enhanced anti-tumor response. Meanwhile, distinct transcriptomic signatures, cytotoxic phenotypes and evolution trajectory of effector CD8+ T cells from early-stage to advanced HCC were also identified. Our study presents a comprehensive insight for dissecting the immune microenvironment in HCC and highlights novel macrophage and T cell subsets that could be further exploited in future immunotherapy. Citation Format: Guohe Song, Yang Shi, Youpei Lin, Juan Zhang, Shuaixi Yang, Qiang Gao. Global immune characterization of hepatocellular carcinoma identifies macrophage and T cell subsets related to disease progression [abstract]. In: Proceedings of the AACR Virtual Special Conference on Tumor Heterogeneity: From Single Cells to Clinical Impact; 2020 Sep 17-18. Philadelphia (PA): AACR; Cancer Res 2020;80(21 Suppl):Abstract nr PO-055.

Molecular characterization of hepatocellular carcinoma in Mongolia delineates unique genomic features

Molecular characterization of hepatocellular carcinoma in Mongolia delineates unique genomic features

Characterization of Hepatocellular Carcinoma Following Direct-Acting Antiviral Therapy: A Prospective Study

Background and aim: Chronic Hepatitis C (CHC) remains the most common cause of Hepatocellular Carcinoma (HCC). Direct-Acting Antiviral (DAA) therapy reduce incident of HCC among HCV-infected patients, however the impact of these therapies on tumor behavior is less clear. Here, we compared the characteristics of HCC diagnosed before and after initiation of f DAA therapy in large population-based cohort. Patients and methods: In a prospective cohort of an outreached program in 73 villages across Egypt, 14,495 (91.2%) patients were treated with DAAs and followed after SVR for median of two years (12-45 months), Of those, 275 patients had HCC (166 patients before and 109 patients after the initiation of DAA therapy). Results: Patients who developed HCC after DAA had less tumor size, portal vein invasion, advanced stage according to BCLC classification and Milan criteria compared to those who developed HCC before therapy (P<0.05, for all comparisons). These findings remained significant independent of age, sex, body mass index (BMI), AFP, viral load and Child-Pugh score (Odds ratio: 0.338; 95% confidence interval: 0.13-0.366; P=0.0001). Conclusion: HCC developed in CHC patients who achieved SVR following DAAs tend to display less aggressive pattern when compared to HCC diagnosed before DAAs therapy.

Characterization of hepatocellular carcinoma in Mexico

Introduction and aimsIn Mexico, complications of cirrhosis are the third leading cause of death in adult males. In recent decades, the incidence of hepatocellular carcinoma has increased worldwide. The aim of this study was to determine the characteristics of patients with hepatocellular carcinoma at two Mexican tertiary care hospitals. Material and methodsAn observational, cross-sectional, retrospective study was conducted between January 2008 and April 2014. We described the clinical features, epidemiologic characteristics, diagnosis, and treatment of patients with hepatocellular carcinoma. ResultsOne hundred and forty-eight patients were included. There was a predominance in males and disease manifestation in the sixth decade of life. Liver disease was associated in 87% of subjects and was mainly attributed to alcohol abuse, hepatitis C infection, and nonalcoholic steatohepatitis. Sixty percent (60%) of cases were classified as Child-Pugh stage A cirrhosis, 75.5% harbored a single tumor at diagnosis, 27.7% had normal alpha-fetoprotein values, and only 39.2% of patients with known liver disease were under a surveillance program. Tumors were larger than 5cm at diagnosis in 64.3% of patients, and well-differentiated lesions were most frequently detected. Over 70% of patients were diagnosed at a non-curative stage. By the 2014 study cutoff point, 77.7% of patients had died. Treatment was determined by the means available at each center and followed the therapeutic recommendations in international guidelines in 45.3% of cases, clearly impacting survival. ConclusionsBetter surveillance methods are required to diagnose the disease at its early stages, but treatment still requires individual adaptation to each center's available resources.

Multiparametric imaging for detection and characterization of hepatocellular carcinoma using gadoxetic acid-enhanced MRI and perfusion-CT: which parameters work best?

BackgroundMRI and perfusion-CT (PCT) are both useful imaging techniques for detection and characterization of liver lesions. The aim of this study was to compare the diagnostic accuracy of imaging parameters derived from PCT and gadoxetic acid-enhanced MRI in patients with hepatocellular carcinoma (HCC).Methods36 patients with liver cirrhosis and a total of 67 lesions referred to our hospital for multi-parametric diagnosis of HCC-suspected liver lesions in the setting of liver cirrhosis were prospectively enrolled and underwent PCT and MRI. HCC diagnosis was confirmed either by histology (n = 60) or interval growth (n = 7). For PCT, mean/max blood flow (BF), blood volume (BV), k-trans, arterial liver perfusion (ALP), portal venous perfusion (PVP) and hepatic perfusion index (HPI) were quantified. Two readers identified the lesions based on single maps each being blinded to the number of lesions.MRI-protocol included fat-suppressed T1w-VIBE sequences obtained before, 2, 5, 10 and 20 min after the injection of gadoxetic acid as well as non-enhanced coronal HASTE, axial T1w-VIBE, fat-suppressed T2w-TSE and DWI. Quantitative analysis was performed using enhancement ratios between tumor and liver parenchyma for post-contrast in the hepatobiliary phase (RIRHB), arterial (ERa) and late-venous (ERv) phases as well as signal intensity ratios (liver/parenchyma) on T1w (RIRT1) and T2w (RIRT2).ResultsIn PCT analysis, all lesions exhibited high BFmax values (63–250 mL/100 g tissue) and were visible on HPI maps with high degrees of arterial blood supply of (HPI > 96%).In MRI, RIRHB was negative in 8/67. 12/67 HCCs were missed on DWI. 46/67 HCCs showed wash-in and 47/67 HCC showed wash-out of contrast agent. 6/67 HCCs were missed on T1w and 11/67 were missed on T2w-sequences when analyzed separately, while analysis of multiparametric MRI combining typical enhancement pattern, visibility on hepatobiliary phase and T1w-images the same number of lesions as PCT irrespective of their size (1–19 cm) were detected. Quantification of early enhancement by ERa or ERv did not improve detection rates.ConclusionsPerfusion-CT and gadoxetic acid-enhanced MRI were comparable in detecting HCC lesions. For PCT a mean HPI > 96% proved to be a very robust parameter for detection and characterization of HCC.

Benign Hepatocellular Nodules: Hepatobiliary Phase of Gadoxetic Acid-enhanced MR Imaging Based on Molecular Background.

Gadoxetic acid is a contrast agent for magnetic resonance (MR) imaging with hepatocyte-specific properties and is becoming increasingly important in detection and characterization of hepatocellular carcinoma and benign hepatocellular nodules, including focal nodular hyperplasia (FNH), nodular regenerative hyperplasia (NRH), hepatocellular adenoma (HCA), and dysplastic nodule. In these hepatocellular nodules, a positive correlation between the grade of membranous uptake transporter organic anion-transporting polypeptide (OATP) 1B3 expression and signal intensity in the hepatobiliary (HB) phase has been verified. In addition, it has been clarified that OATP1B3 expression is regulated by activation of β-catenin and/or hepatocyte nuclear factor 4α. On the other hand, recent studies have also revealed some of the background molecular mechanisms of benign hepatocellular nodules. FNH commonly shows iso- or hyperintensity in the HB phase with equal or stronger OATP1B3 expression, with map-like distribution of glutamine synthetase (a target of Wnt/β-catenin signaling) and OATP1B3 expression. NRH shows doughnut-like enhancement with hypointensity in the central portion in the HB phase with OATP1B3 expression. The majority of HCAs show hypointensity in the HB phase, but β-catenin-activated HCA exclusively demonstrates iso- or hyperintensity with increased expression of nuclear β-catenin, glutamine synthetase, and OATP1B3. Dysplastic nodule commonly shows iso- or hyperintensity in the HB phase with similar to increased OATP1B3 expression, but one-third of high-grade dysplastic nodules can be demonstrated as a hypointense nodule with decreased OATP1B3 expression. Knowledge of these background molecular mechanisms of gadoxetic acid-enhanced MR imaging is important not only for precise imaging diagnosis but also understanding of the pathogenesis of benign hepatocellular nodules. ©RSNA, 2016.

Comprehensive genomic characterization of hepatocellular carcinoma to reveal novel therapeutic targets.

e15643Background: Hepatocellular carcinoma (HCC) is the most prevalent primary liver cancer, which is particularly common in certain regions of Asia. Here we report the transcriptome and whole exom...

Characterization of Hepatocellular Carcinoma Using CT Intensity and K-means

Characterization of Hepatocellular Carcinoma Using CT Intensity and K-means

Role of dual energy spectral computed tomography in characterization of hepatocellular carcinoma: Initial experience from a tertiary liver care institute

ObjectiveTo investigate dual-energy spectral CT in characterization of hepatocellular Carcinoma (HCC) in patients with chronic liver disease. MethodsDynamic computed tomography (CT) was performed in 3600 patients (2879 males; 721 females, mean age 50.9±11.9 years) with working clinical diagnosis of liver cirrhosis for hepatocellular carcinoma screening and other clinical indications. The study was conducted over a period of 3 years. During dynamic CT scanning, spectral (monochromatic) and routine (polychromatic) CT acquisitions were obtained on a single tube, dual energy, 64 slice multi-detector CT scanner. Imaging findings were studied on routine CT. On the basis of routine CT findings, indeterminate lesions (lesions not showing characteristic hypervascularity followed by washout on dynamic routine CT scan) that were referred for biopsy or surgery were segregated. A retrospective blinded review of the lesions, acquired by the spectral CT acquisitions was done with the help of gem stone imaging (GSI) software to characterize these lesions. All the above lesions were analyzed qualitatively in the arterial phase for lesion conspicuity as well as quantitatively using the monochromatic data sets and nodule Iodine concentration on material density maps, respectively. This data was studied with respect to predictability of HCC using the spectral CT technique. Iodine density of the lesion, surrounding liver parenchyma, and lesion to liver parenchyma ratio (LLR) were derived and statistically analyzed. Histopathology of the lesion in question was treated as gold standard for analysis. ResultsIt was observed via statistical analysis that the value of iodine density of the lesion on material density sets of ≥29.5mg/dl, enabled a discriminatory power of 86.5%, sensitivity of 90.5% with 95% confidence Interval (CI) (69.2–98.8%) and specificity of 81.2% with 95% Confidence Interval (54.4–95.9%) in predicting HCC. Qualitative assessment also showed higher lesion conspicuity with spectral CT image sets as compared to routine CT data. ConclusionThis study reveals that spectral imaging is an excellent qualitative as well as a quantitative tool for assessing and predicting hepatocellular carcinoma in cirrhotic patients.

Triphasic CT Liver Characterization and Color Data Fusion

The aim of the present work is the analysis and mining of the informative content related to pathological liver tissues, when acquired by triphasic CT, with the proposal of a data-fusion approach, which is able to visualize and show up such a content in the best way as a support to the medical diagnosis. Since the huge amount of CT volumes to be analyzed in a limited time is the major cause of sensitivity loss during the diagnosis process, a better chance of detection and localization of the pathology can be derived from the method here proposed. This method can be a valid support to the current medical practice, even in the cases where pathology is at the very early stage and has a large probability to be missed by a visual inspection. As expected when analyzing the three phase volumes, one can note that the injection of a contrast agent causes significant changes in the radiological finding for both pathological and healthy parts of the liver. Thanks to a specific statistical analysis performed on a training dataset of real cases, the described study was focused on the characterization of hepatocellular carcinoma (HCC) tumor tissues and liver tissues. In order to detect and discriminate tumor from liver parenchyma, we here propose using both steady-state and dynamic features. Some common patterns have been observed suggesting rules, which have been confirmed by radiology specialists. Based on the rules and the best discriminant power of some of the characterizing features, a new color data fusion approach is then proposed and discussed which improves the mass visibility while increasing contrast with respect to surrounding parenchyma.

Characterization of hepatocellular carcinoma (HCC) lesions using a novel CT-based volume perfusion (VPCT) technique

ObjectiveTo characterize hepatocellular carcinoma (HCC) in terms of perfusion parameters using volume perfusion CT (VPCT) and two different calculation methods, compare their results, look for interobserver agreement of measurements and correlation between tumor arterialization and lesion size. Material and methodsThis study was part of a prospective monitoring study in patients with HCC undergoing TACE, which was approved by the local Institutional Review Board. 79 HCC-patients (mean age, 64.7) with liver cirrhosis were enrolled. VPCT was performed for 40s covering the involved liver (80kV, 100/120mAs) using 64mm×0.6mm collimation, 26 consecutive volume measurements, 50mL iodinated contrast IV and 5mL/s flow rate. Mean/maximum blood flow (BF; ml/100mL/min), blood volume (BV) and k-trans were determined both with the maximum slope+Patlak vs. deconvolution method. Additionally, the portal venous liver perfusion (PVP), the arterial liver perfusion (ALP) and the hepatic perfusion index (HPI) were determined for each tumor including size measurements. Interobserver agreement for all perfusion parameters was calculated using intraclass correlation coefficients (ICC). ResultsThe max. slope+Patlak method yielded: BFmean/max=37.8/57mL/100g-tissue/′, BVmean/max=9.8/11.1mL/100g-tissue, k-trans-mean/max=34.4/44.5mL/100g-tissue/′. For the deconvolution method BFmean/max, BVmean/max and, k-trans-mean/max were 68.3/106.1mL/100g-tissue/′, 12.6/15.5mL/100g-tissue and 24/33.8mL/100g-tissue/′. Mean ALP, PVP, HPI and size were 53.7mL/100g-tissue/′, 2.4mL/100g-tissue/′, 96.4 and 3.5cm, respectively. Interobserver agreement measured with intraclass coefficient correlation (ICC) was very good for all perfusion parameters (≥0.99). Best correlation between calculation methods was achieved for measurements of BF, while BV and k-trans values were less correlated. There was no relationship between HPI and lesion size. ConclusionVPCT can measure tumor volume perfusion non-invasively and enables quantification of the degree of HCC arterialization. Results are dependent on the technique used with best inter-method correlation for BF. Tumor HPI did not proved size-dependent.

Description of focal liver lesions with Gd-EOB-DTPA enhanced MRI.

Imaging procedures play a fundamental role in the therapeutic management of focal liver lesions. The goals of imaging are to detect and correctly characterize focal liver lesions. This review highlights the performances of newer, liver-specific, contrast media in the diagnosis of focal liver lesions, particularly Gd-EOB-DTPA (Primovist), the most frequently used liver specific contrast media.It has been shown, in different papers, that Gd-EOB-DTPA has better performances compared to either triphasic contrast enhanced computed tomography or dynamic MRI in both detection and characterization of hepatocellular carcinoma on the cirrhotic liver. Therefore liver MRI with Primovist is considered, in many centers, the “state-of-the-art” imaging examination of the liver before surgery or liver transplantation.Gd-EOB-DTPA is also useful in the differential diagnosis of benign hypervascular focal liver lesions such as adenomas or focal nodular hyperplasias.

Hepatobiliary contrast agents: differential diagnosis of focal hepatic lesions, pitfalls and other indications.

The characterization of focal liver lesions is very important. Magnetic resonance imaging is considered the best imaging method for evaluating such lesions, but does not allow for the diagnosis in all cases. The use of hepatobiliary contrast agents increases the diagnostic accuracy of magnetic resonance imaging and reduces the number of non-specific liver lesions. The main indications for the method include: differentiation between focal nodular hyperplasia and adenoma; characterization of hepatocellular carcinomas in cirrhotic patients; detection of small liver metastases; evaluation of biliary anatomy; and characterization of postoperative biliary fistulas. The use of hepatobiliary contrast agents may reduce the need for invasive diagnostic procedures and further investigations with other imaging methods, besides the need for imaging follow-up.

Characterization of Primary and Secondary Malignant Liver Lesions from B-Mode Ultrasound

Characterization of hepatocellular carcinomas (HCCs) and metastatic carcinomas (METs) from B-mode ultrasound presents a daunting challenge for radiologists due to their highly overlapping appearances. The differential diagnosis between HCCs and METs is often carried out by observing the texture of regions inside the lesion and the texture of background liver on which the lesion has evolved. The present study investigates the contribution made by texture patterns of regions inside and outside of the lesions for binary classification between HCC and MET lesions. The study is performed on 51 real ultrasound liver images with 54 malignant lesions, i.e., 27 images with 27 solitary HCCs (13 small HCCs and 14 large HCCs) and 24 images with 27 MET lesions (12 typical cases and 15 atypical cases). A total of 120 within-lesion regions of interest and 54 surrounding lesion regions of interest are cropped from 54 lesions. Subsequently, 112 texture features (56 texture features and 56 texture ratio features) are computed by statistical, spectral, and spatial filtering based texture features extraction methods. A two-step methodology is used for feature set optimization, i.e., feature pruning by removal of nondiscriminatory features followed by feature selection by genetic algorithm-support vector machine (SVM) approach. The SVM classifier is designed based on optimum features. The proposed computer-aided diagnostic system achieved the overall classification accuracy of 91.6% with sensitivity of 90% and 93.3% for HCCs and METs, respectively. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in diagnosing liver malignancies.